A non-local capsule neural network for hyperspectral remote sensing image classification

ABSTRACT

In this study, we introduce a non-local block of the attention mechanism into capsule neural network (CapsNet) to form a non-local capsule network (NLCapsNet) for hyperspectral remote sensing image (HSI) classification. The presented NLCapsNet uses global information from input images and has a powerful representation of the capacity and spatial relationships among HSI features. It can effectively isolate invalid information and consolidate valid information, in addition to learning more representative features and capturing the long-distance dependencies of HSIs with only a few layers. An additional convolutional layer is embedded before the capsule layers to capture high-level features and speed up the routing procedure. The proposed method can effectively enhance the classification accuracy with a rapid convergence speed and avoid overfitting when the number of training samples is limited. The NLCapsNet performs well on the classification of the Kennedy Space Center, Pavia University and Salinas datasets.

KEYWORDS:

• Capsule neural network
• convolutional neural network
• hyperspectral image classification
• non-local operation

Additional information

Funding

This work was supported by the National Natural Science Foundation of China [41631177 and 41671393]; Construction project of excellent teaching materials for Postgraduates of Hefei University of Technology [2019YJC03].